@inproceedings{yadav-etal-2021-want,
title = "If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering",
author = "Yadav, Vikas and
Bethard, Steven and
Surdeanu, Mihai",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.363/",
doi = "10.18653/v1/2021.naacl-main.363",
pages = "4571--4581",
abstract = "Multi-hop reasoning requires aggregation and inference from multiple facts. To retrieve such facts, we propose a simple approach that retrieves and reranks set of evidence facts jointly. Our approach first generates unsupervised clusters of sentences as candidate evidence by accounting links between sentences and coverage with the given query. Then, a RoBERTa-based reranker is trained to bring the most representative evidence cluster to the top. We specifically emphasize on the importance of retrieving evidence jointly by showing several comparative analyses to other methods that retrieve and rerank evidence sentences individually. First, we introduce several attention- and embedding-based analyses, which indicate that jointly retrieving and reranking approaches can learn compositional knowledge required for multi-hop reasoning. Second, our experiments show that jointly retrieving candidate evidence leads to substantially higher evidence retrieval performance when fed to the same supervised reranker. In particular, our joint retrieval and then reranking approach achieves new state-of-the-art evidence retrieval performance on two multi-hop question answering (QA) datasets: 30.5 Recall@2 on QASC, and 67.6{\%} F1 on MultiRC. When the evidence text from our joint retrieval approach is fed to a RoBERTa-based answer selection classifier, we achieve new state-of-the-art QA performance on MultiRC and second best result on QASC."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yadav-etal-2021-want">
<titleInfo>
<title>If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vikas</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Surdeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-hop reasoning requires aggregation and inference from multiple facts. To retrieve such facts, we propose a simple approach that retrieves and reranks set of evidence facts jointly. Our approach first generates unsupervised clusters of sentences as candidate evidence by accounting links between sentences and coverage with the given query. Then, a RoBERTa-based reranker is trained to bring the most representative evidence cluster to the top. We specifically emphasize on the importance of retrieving evidence jointly by showing several comparative analyses to other methods that retrieve and rerank evidence sentences individually. First, we introduce several attention- and embedding-based analyses, which indicate that jointly retrieving and reranking approaches can learn compositional knowledge required for multi-hop reasoning. Second, our experiments show that jointly retrieving candidate evidence leads to substantially higher evidence retrieval performance when fed to the same supervised reranker. In particular, our joint retrieval and then reranking approach achieves new state-of-the-art evidence retrieval performance on two multi-hop question answering (QA) datasets: 30.5 Recall@2 on QASC, and 67.6% F1 on MultiRC. When the evidence text from our joint retrieval approach is fed to a RoBERTa-based answer selection classifier, we achieve new state-of-the-art QA performance on MultiRC and second best result on QASC.</abstract>
<identifier type="citekey">yadav-etal-2021-want</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.363</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.363/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>4571</start>
<end>4581</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering
%A Yadav, Vikas
%A Bethard, Steven
%A Surdeanu, Mihai
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F yadav-etal-2021-want
%X Multi-hop reasoning requires aggregation and inference from multiple facts. To retrieve such facts, we propose a simple approach that retrieves and reranks set of evidence facts jointly. Our approach first generates unsupervised clusters of sentences as candidate evidence by accounting links between sentences and coverage with the given query. Then, a RoBERTa-based reranker is trained to bring the most representative evidence cluster to the top. We specifically emphasize on the importance of retrieving evidence jointly by showing several comparative analyses to other methods that retrieve and rerank evidence sentences individually. First, we introduce several attention- and embedding-based analyses, which indicate that jointly retrieving and reranking approaches can learn compositional knowledge required for multi-hop reasoning. Second, our experiments show that jointly retrieving candidate evidence leads to substantially higher evidence retrieval performance when fed to the same supervised reranker. In particular, our joint retrieval and then reranking approach achieves new state-of-the-art evidence retrieval performance on two multi-hop question answering (QA) datasets: 30.5 Recall@2 on QASC, and 67.6% F1 on MultiRC. When the evidence text from our joint retrieval approach is fed to a RoBERTa-based answer selection classifier, we achieve new state-of-the-art QA performance on MultiRC and second best result on QASC.
%R 10.18653/v1/2021.naacl-main.363
%U https://aclanthology.org/2021.naacl-main.363/
%U https://doi.org/10.18653/v1/2021.naacl-main.363
%P 4571-4581
Markdown (Informal)
[If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering](https://aclanthology.org/2021.naacl-main.363/) (Yadav et al., NAACL 2021)
ACL